Urban-StyleGAN: Learning to Generate and Manipulate Images of Urban Scenes

by   George Eskandar, et al.

A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple objects is understudied. While some frameworks produce high-quality street scenes with little to no control over the image content, others offer more control at the expense of high-quality generation. A common limitation of both approaches is the use of global latent codes for the whole image, which hinders the learning of independent object distributions. Motivated by SemanticStyleGAN (SSG), a recent work on latent space disentanglement in human face generation, we propose a novel framework, Urban-StyleGAN, for urban scene generation and manipulation. We find that a straightforward application of SSG leads to poor results because urban scenes are more complex than human faces. To provide a more compact yet disentangled latent representation, we develop a class grouping strategy wherein individual classes are grouped into super-classes. Moreover, we employ an unsupervised latent exploration algorithm in the 𝒮-space of the generator and show that it is more efficient than the conventional 𝒲^+-space in controlling the image content. Results on the Cityscapes and Mapillary datasets show the proposed approach achieves significantly more controllability and improved image quality than previous approaches on urban scenes and is on par with general-purpose non-controllable generative models (like StyleGAN2) in terms of quality.


page 1

page 6

page 7


High Quality Bidirectional Generative Adversarial Networks

Generative adversarial networks (GANs) have achieved outstanding success...

StyleT2F: Generating Human Faces from Textual Description Using StyleGAN2

AI-driven image generation has improved significantly in recent years. G...

Semantic-Guided Inpainting Network for Complex Urban Scenes Manipulation

Manipulating images of complex scenes to reconstruct, insert and/or remo...

LOPR: Latent Occupancy PRediction using Generative Models

Environment prediction frameworks are essential for autonomous vehicles ...

Collaging Class-specific GANs for Semantic Image Synthesis

We propose a new approach for high resolution semantic image synthesis. ...

Towards Pragmatic Semantic Image Synthesis for Urban Scenes

The need for large amounts of training and validation data is a huge con...

Evolution of Images with Diversity and Constraints Using a Generator Network

Evolutionary search has been extensively used to generate artistic image...

Please sign up or login with your details

Forgot password? Click here to reset